October 17, 2019

3027 words 15 mins read

Paper Group ANR 885

Black Box FDR. Transductive Label Augmentation for Improved Deep Network Learning. Reproducibility Report for “Learning To Count Objects In Natural Images For Visual Question Answering”. Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registration. Global Convergence of EM Algorithm for Mixtures of Two Component Linear Regr …

Black Box FDR


Title	Black Box FDR
Authors	Wesley Tansey, Yixin Wang, David M. Blei, Raul Rabadan
Abstract	Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment. BB-FDR learns a series of black box predictive models to boost power and control the false discovery rate (FDR) at two stages of study analysis. In Stage 1, it uses a deep neural network prior to report which experiments yielded significant outcomes. In Stage 2, a separate black box model of each covariate is used to select features that have significant predictive power across all experiments. In benchmarks, BB-FDR outperforms competing state-of-the-art methods in both stages of analysis. We apply BB-FDR to two real studies on cancer drug efficacy. For both studies, BB-FDR increases the proportion of significant outcomes discovered and selects variables that reveal key genomic drivers of drug sensitivity and resistance in cancer.
Tasks
Published	2018-06-08
URL	http://arxiv.org/abs/1806.03143v1
PDF	http://arxiv.org/pdf/1806.03143v1.pdf
PWC	https://paperswithcode.com/paper/black-box-fdr
Repo
Framework

Transductive Label Augmentation for Improved Deep Network Learning


Title	Transductive Label Augmentation for Improved Deep Network Learning
Authors	Ismail Elezi, Alessandro Torcinovich, Sebastiano Vascon, Marcello Pelillo
Abstract	A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to the large number of trainable parameters, they will very likely be subject to overfitting phenomena. On the other hand, the increment of the training set size through further manual or semi-automatic labellings can be costly, if not possible at times. Thus, the standard techniques to address this issue are transfer learning and data augmentation, which consists of applying some sort of “transformation” to existing labeled instances to let the training set grow in size. Although this approach works well in applications such as image classification, where it is relatively simple to design suitable transformation operators, it is not obvious how to apply it in more structured scenarios. Motivated by the observation that in virtually all application domains it is easy to obtain unlabeled data, in this paper we take a different perspective and propose a \emph{label augmentation} approach. We start from a small, curated labeled dataset and let the labels propagate through a larger set of unlabeled data using graph transduction techniques. This allows us to naturally use (second-order) similarity information which resides in the data, a source of information which is typically neglected by standard augmentation techniques. In particular, we show that by using known game theoretic transductive processes we can create larger and accurate enough labeled datasets which use results in better trained neural networks. Preliminary experiments are reported which demonstrate a consistent improvement over standard image classification datasets.
Tasks	Data Augmentation, Image Classification, Transfer Learning
Published	2018-05-26
URL	http://arxiv.org/abs/1805.10546v1
PDF	http://arxiv.org/pdf/1805.10546v1.pdf
PWC	https://paperswithcode.com/paper/transductive-label-augmentation-for-improved
Repo
Framework

Reproducibility Report for “Learning To Count Objects In Natural Images For Visual Question Answering”


Title	Reproducibility Report for “Learning To Count Objects In Natural Images For Visual Question Answering”
Authors	Shagun Sodhani, Vardaan Pahuja
Abstract	This is the reproducibility report for the paper “Learning To Count Objects In Natural Images For Visual QuestionAnswering”
Tasks	Question Answering, Visual Question Answering
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08174v1
PDF	http://arxiv.org/pdf/1805.08174v1.pdf
PWC	https://paperswithcode.com/paper/reproducibility-report-for-learning-to-count
Repo
Framework

Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registration


Title	Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registration
Authors	Julian Krebs, Tommaso Mansi, Boris Mailhé, Nicholas Ayache, Hervé Delingette
Abstract	We propose a deformable registration algorithm based on unsupervised learning of a low-dimensional probabilistic parameterization of deformations. We model registration in a probabilistic and generative fashion, by applying a conditional variational autoencoder (CVAE) network. This model enables to also generate normal or pathological deformations of any new image based on the probabilistic latent space. Most recent learning-based registration algorithms use supervised labels or deformation models, that miss important properties such as diffeomorphism and sufficiently regular deformation fields. In this work, we constrain transformations to be diffeomorphic by using a differentiable exponentiation layer with a symmetric loss function. We evaluated our method on 330 cardiac MR sequences and demonstrate robust intra-subject registration results comparable to two state-of-the-art methods but with more regular deformation fields compared to a recent learning-based algorithm. Our method reached a mean DICE score of 78.3% and a mean Hausdorff distance of 7.9mm. In two preliminary experiments, we illustrate the model’s abilities to transport pathological deformations to healthy subjects and to cluster five diseases in the unsupervised deformation encoding space with a classification performance of 70%.
Tasks
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07172v2
PDF	http://arxiv.org/pdf/1804.07172v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-probabilistic-deformation
Repo
Framework

Global Convergence of EM Algorithm for Mixtures of Two Component Linear Regression


Title	Global Convergence of EM Algorithm for Mixtures of Two Component Linear Regression
Authors	Jeongyeol Kwon, Wei Qian, Constantine Caramanis, Yudong Chen, Damek Davis
Abstract	The Expectation-Maximization algorithm is perhaps the most broadly used algorithm for inference of latent variable problems. A theoretical understanding of its performance, however, largely remains lacking. Recent results established that EM enjoys global convergence for Gaussian Mixture Models. For Mixed Linear Regression, however, only local convergence results have been established, and those only for the high SNR regime. We show here that EM converges for mixed linear regression with two components (it is known that it may fail to converge for three or more), and moreover that this convergence holds for random initialization. Our analysis reveals that EM exhibits very different behavior in Mixed Linear Regression from its behavior in Gaussian Mixture Models, and hence our proofs require the development of several new ideas.
Tasks
Published	2018-10-12
URL	https://arxiv.org/abs/1810.05752v4
PDF	https://arxiv.org/pdf/1810.05752v4.pdf
PWC	https://paperswithcode.com/paper/global-convergence-of-em-algorithm-for
Repo
Framework

Size-to-depth: A New Perspective for Single Image Depth Estimation


Title	Size-to-depth: A New Perspective for Single Image Depth Estimation
Authors	Yiran Wu, Sihao Ying, Lianmin Zheng
Abstract	In this paper we consider the problem of single monocular image depth estimation. It is a challenging problem due to its ill-posedness nature and has found wide application in industry. Previous efforts belongs roughly to two families: learning-based method and interactive method. Learning-based method, in which deep convolutional neural network (CNN) is widely used, can achieve good result. But they suffer low generalization ability and typically perform poorly for unfamiliar scenes. Besides, data-hungry nature for such method makes data aquisition expensive and time-consuming. Interactive method requires human annotation of depth which, however, is errorneous and of large variance. To overcome these problems, we propose a new perspective for single monocular image depth estimation problem: size to depth. Our method require sparse label for real-world size of object rather than raw depth. A Coarse depth map is then inferred following geometric relationships according to size labels. Then we refine the depth map by doing energy function optimization on conditional random field(CRF). We experimentally demonstrate that our method outperforms traditional depth-labeling methods and can produce satisfactory depth maps.
Tasks	Depth Estimation
Published	2018-01-13
URL	http://arxiv.org/abs/1801.04461v1
PDF	http://arxiv.org/pdf/1801.04461v1.pdf
PWC	https://paperswithcode.com/paper/size-to-depth-a-new-perspective-for-single
Repo
Framework

A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices


Title	A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
Authors	Till Speicher, Hoda Heidari, Nina Grgic-Hlaca, Krishna P. Gummadi, Adish Singla, Adrian Weller, Muhammad Bilal Zafar
Abstract	Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine which of the two is more unfair? Our core idea is to use existing inequality indices from economics to measure how unequally the outcomes of an algorithm benefit different individuals or groups in a population. Our work offers a justified and general framework to compare and contrast the (un)fairness of algorithmic predictors. This unifying approach enables us to quantify unfairness both at the individual and the group level. Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component. Earlier methods are typically designed to tackle only between-group unfairness, which may be justified for legal or other reasons. However, we demonstrate that minimizing exclusively the between-group component may, in fact, increase the within-group, and hence the overall unfairness. We characterize and illustrate the tradeoffs between our measures of (un)fairness and the prediction accuracy.
Tasks	Decision Making
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00787v1
PDF	http://arxiv.org/pdf/1807.00787v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-approach-to-quantifying-algorithmic
Repo
Framework

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders


Title	Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
Authors	Tengfei Ma, Jie Chen, Cao Xiao
Abstract	Deep generative models have achieved remarkable success in various data domains, including images, time series, and natural languages. There remain, however, substantial challenges for combinatorial structures, including graphs. One of the key challenges lies in the difficulty of ensuring semantic validity in context. For examples, in molecular graphs, the number of bonding-electron pairs must not exceed the valence of an atom; whereas in protein interaction networks, two proteins may be connected only when they belong to the same or correlated gene ontology terms. These constraints are not easy to be incorporated into a generative model. In this work, we propose a regularization framework for variational autoencoders as a step toward semantic validity. We focus on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints. Experimental results confirm a much higher likelihood of sampling valid graphs in our approach, compared with others reported in the literature.
Tasks	Time Series
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02630v2
PDF	http://arxiv.org/pdf/1809.02630v2.pdf
PWC	https://paperswithcode.com/paper/constrained-generation-of-semantically-valid
Repo
Framework

Game AI Research with Fast Planet Wars Variants


Title	Game AI Research with Fast Planet Wars Variants
Authors	Simon M. Lucas
Abstract	This paper describes a new implementation of Planet Wars, designed from the outset for Game AI research. The skill-depth of the game makes it a challenge for game-playing agents, and the speed of more than 1 million game ticks per second enables rapid experimentation and prototyping. The parameterised nature of the game together with an interchangeable actuator model make it well suited to automated game tuning. The game is designed to be fun to play for humans, and is directly playable by General Video Game AI agents.
Tasks
Published	2018-06-22
URL	http://arxiv.org/abs/1806.08544v1
PDF	http://arxiv.org/pdf/1806.08544v1.pdf
PWC	https://paperswithcode.com/paper/game-ai-research-with-fast-planet-wars
Repo
Framework

Wearable Audio and IMU Based Shot Detection in Racquet Sports


Title	Wearable Audio and IMU Based Shot Detection in Racquet Sports
Authors	Manish Sharma, Akash Anand, Rupika Srivastava, Lakshmi Kaligounder
Abstract	Wearables like smartwatches which are embedded with sensors and powerful processors, provide a strong platform for development of analytics solutions in sports domain. To analyze players’ games, while motion sensor based shot detection has been extensively studied in sports like Tennis, Golf, Baseball; Table Tennis and Badminton are relatively less explored due to possible less intense hand motion during shots. In our paper, we propose a novel, computationally inexpensive and real-time system for shot detection in table tennis, based on fusion of Inertial Measurement Unit (IMU) and audio sensor data embedded in a wrist-worn wearable. The system builds upon our presented methodology for synchronizing IMU and audio sensor input in time using detected shots and achieves 95.6% accuracy. To our knowledge, it is the first fusion-based solution for sports analysis in wearables. Shot detectors for other racquet sports as well as further analytics to provide features like shot classification, rally analysis and recommendations, can easily be built over our proposed solution.
Tasks
Published	2018-05-14
URL	http://arxiv.org/abs/1805.05456v1
PDF	http://arxiv.org/pdf/1805.05456v1.pdf
PWC	https://paperswithcode.com/paper/wearable-audio-and-imu-based-shot-detection
Repo
Framework

Dictionary Learning by Dynamical Neural Networks


Title	Dictionary Learning by Dynamical Neural Networks
Authors	Tsung-Han Lin, Ping Tak Peter Tang
Abstract	A dynamical neural network consists of a set of interconnected neurons that interact over time continuously. It can exhibit computational properties in the sense that the dynamical system’s evolution and/or limit points in the associated state space can correspond to numerical solutions to certain mathematical optimization or learning problems. Such a computational system is particularly attractive in that it can be mapped to a massively parallel computer architecture for power and throughput efficiency, especially if each neuron can rely solely on local information (i.e., local memory). Deriving gradients from the dynamical network’s various states while conforming to this last constraint, however, is challenging. We show that by combining ideas of top-down feedback and contrastive learning, a dynamical network for solving the l1-minimizing dictionary learning problem can be constructed, and the true gradients for learning are provably computable by individual neurons. Using spiking neurons to construct our dynamical network, we present a learning process, its rigorous mathematical analysis, and numerical results on several dictionary learning problems.
Tasks	Dictionary Learning
Published	2018-05-23
URL	http://arxiv.org/abs/1805.08952v1
PDF	http://arxiv.org/pdf/1805.08952v1.pdf
PWC	https://paperswithcode.com/paper/dictionary-learning-by-dynamical-neural
Repo
Framework

Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method


Title	Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method
Authors	Wei Li, Zheng Yang, Xu Sun
Abstract	Traditional Chinese Medicine (TCM) is an influential form of medical treatment in China and surrounding areas. In this paper, we propose a TCM prescription generation task that aims to automatically generate a herbal medicine prescription based on textual symptom descriptions. Sequence-to-sequence (seq2seq) model has been successful in dealing with sequence generation tasks. We explore a potential end-to-end solution to the TCM prescription generation task using seq2seq models. However, experiments show that directly applying seq2seq model leads to unfruitful results due to the repetition problem. To solve the problem, we propose a novel decoder with coverage mechanism and a novel soft loss function. The experimental results demonstrate the effectiveness of the proposed approach. Judged by professors who excel in TCM, the generated prescriptions are rated 7.3 out of 10. It shows that the model can indeed help with the prescribing procedure in real life.
Tasks
Published	2018-01-27
URL	http://arxiv.org/abs/1801.09030v2
PDF	http://arxiv.org/pdf/1801.09030v2.pdf
PWC	https://paperswithcode.com/paper/exploration-on-generating-traditional-chinese
Repo
Framework

A Taxonomy for Neural Memory Networks


Title	A Taxonomy for Neural Memory Networks
Authors	Ying Ma, Jose Principe
Abstract	In this paper, a taxonomy for memory networks is proposed based on their memory organization. The taxonomy includes all the popular memory networks: vanilla recurrent neural network (RNN), long short term memory (LSTM ), neural stack and neural Turing machine and their variants. The taxonomy puts all these networks under a single umbrella and shows their relative expressive power , i.e. vanilla RNN <=LSTM<=neural stack<=neural RAM. The differences and commonality between these networks are analyzed. These differences are also connected to the requirements of different tasks which can give the user instructions of how to choose or design an appropriate memory network for a specific task. As a conceptual simplified class of problems, four tasks of synthetic symbol sequences: counting, counting with interference, reversing and repeat counting are developed and tested to verify our arguments. And we use two natural language processing problems to discuss how this taxonomy helps choosing the appropriate neural memory networks for real world problem.
Tasks
Published	2018-05-01
URL	http://arxiv.org/abs/1805.00327v1
PDF	http://arxiv.org/pdf/1805.00327v1.pdf
PWC	https://paperswithcode.com/paper/a-taxonomy-for-neural-memory-networks
Repo
Framework

Continual State Representation Learning for Reinforcement Learning using Generative Replay


Title	Continual State Representation Learning for Reinforcement Learning using Generative Replay
Authors	Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
Abstract	We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state’s information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to use Variational Auto-Encoders for state representation, and Generative Replay, i.e. the use of generated samples, to maintain past knowledge. We also provide a general and statistically sound method for automatic environment change detection. Our method provides efficient state representation as well as forward transfer, and avoids catastrophic forgetting. The resulting model is capable of incrementally learning information without using past data and with a bounded system size.
Tasks	Representation Learning
Published	2018-10-09
URL	http://arxiv.org/abs/1810.03880v3
PDF	http://arxiv.org/pdf/1810.03880v3.pdf
PWC	https://paperswithcode.com/paper/continual-state-representation-learning-for
Repo
Framework

Autonomous Ramp Merge Maneuver Based on Reinforcement Learning with Continuous Action Space


Title	Autonomous Ramp Merge Maneuver Based on Reinforcement Learning with Continuous Action Space
Authors	Pin Wang, Ching-Yao Chan
Abstract	Ramp merging is a critical maneuver for road safety and traffic efficiency. Most of the current automated driving systems developed by multiple automobile manufacturers and suppliers are typically limited to restricted access freeways only. Extending the automated mode to ramp merging zones presents substantial challenges. One is that the automated vehicle needs to incorporate a future objective (e.g. a successful and smooth merge) and optimize a long-term reward that is impacted by subsequent actions when executing the current action. Furthermore, the merging process involves interaction between the merging vehicle and its surrounding vehicles whose behavior may be cooperative or adversarial, leading to distinct merging countermeasures that are crucial to successfully complete the merge. In place of the conventional rule-based approaches, we propose to apply reinforcement learning algorithm on the automated vehicle agent to find an optimal driving policy by maximizing the long-term reward in an interactive driving environment. Most importantly, in contrast to most reinforcement learning applications in which the action space is resolved as discrete, our approach treats the action space as well as the state space as continuous without incurring additional computational costs. Our unique contribution is the design of the Q-function approximation whose format is structured as a quadratic function, by which simple but effective neural networks are used to estimate its coefficients. The results obtained through the implementation of our training platform demonstrate that the vehicle agent is able to learn a safe, smooth and timely merging policy, indicating the effectiveness and practicality of our approach.
Tasks
Published	2018-03-25
URL	http://arxiv.org/abs/1803.09203v1
PDF	http://arxiv.org/pdf/1803.09203v1.pdf
PWC	https://paperswithcode.com/paper/autonomous-ramp-merge-maneuver-based-on
Repo
Framework